BMW Case Study - Gabe Campbell
Lumin Digital • 2021 - Present Google • 2020 - 2021 BMW • 2018 - 2020

Smart Charging for a Smarter Grid

How I pioneered BMW's first dynamic charging system, using machine learning to balance power grid load while creating a delightful experience for electric vehicle drivers.

First Dynamic Charging
$4.2M Revenue Generated
87% Grid Load Reduced

The Challenge

Electric vehicles were creating a new problem: everyone charged at the same time.

As BMW launched their electric vehicle line, we discovered an unexpected issue. Most drivers plugged in their cars between 6-8 PM, creating massive spikes in power demand. This threatened to overwhelm power grids and increase electricity costs for everyone.

We needed to create an app that would intelligently distribute charging throughout the night while ensuring every driver had a full battery by morning. The challenge? Making grid optimization feel magical, not restrictive.

Power Grid Load Throughout the Day

Peak demand between 6-8 PM was threatening grid stability

12 AM
6 AM
12 PM
6 PM
11 PM

The Solution

An intelligent system that makes doing the right thing feel effortless.

🧠

Predictive Charging Algorithm

Co-developed a machine learning algorithm that predicted optimal charging times based on grid load, electricity prices, and individual driving patterns. The system learned each driver's routine to ensure their car was always ready when needed.

⚡

Transparent User Control

Designed an interface that gave drivers full visibility and control. They could see exactly when their car would charge, override the schedule anytime, and understand how their choices impacted both their wallet and the environment.

🎮

Incentive Design

Created a rewards system that made grid-friendly charging feel like winning. Drivers earned points for off-peak charging, which translated to real savings and exclusive BMW perks.

The Intelligence Behind It

How machine learning made complex optimization feel simple.

Dynamic Charging Algorithm Flow

📊

Grid Analysis

Real-time monitoring of power demand

🚗

Driver Patterns

Learning individual routines

💰

Price Optimization

Finding cheapest charging times

⚡

Smart Schedule

Optimized charging plan

The Driver Experience

Making smart charging feel natural, not technical.

🏠

Coming Home

Driver plugs in their BMW. The app automatically detects connection and shows a friendly greeting with their optimized charging plan for tonight.

📱

Smart Scheduling

The app displays when charging will start, estimated completion time, and potential savings. One tap to approve or adjust based on tomorrow's needs.

🌙

Overnight Magic

While they sleep, the car charges during optimal grid times. Morning notification shows a full battery, money saved, and environmental impact reduced.

The Impact

Real results that transformed how people think about charging.

⚡
87% Peak Load Reduction
💰
$840 Avg Annual Savings
😊
94% User Satisfaction
🌍
2.3M kg CO2 Reduced
"This app made me feel like I was part of the solution, not the problem. Smart charging just became part of my routine."
— BMW i3 Driver, Beta Tester

Project Timeline

From concept to launch in 9 months.

Month 1-2

Research & Discovery

Interviewed 50+ EV drivers, analyzed grid data, identified peak load problem

Month 3-4

Algorithm Development

Co-created ML model with data scientists, tested charging predictions

Month 5-6

Design & Prototyping

Created interface designs, tested with users, refined based on feedback

Month 7-8

Beta Testing

Launched with 500 drivers, gathered data, optimized algorithm

Month 9

Launch

Rolled out to all BMW electric vehicle owners

Key Learnings

What building the future of mobility taught me.

Make the right choice the easy choice.

By optimizing for user convenience first, we achieved grid optimization as a natural outcome.

Transparency builds trust.

Showing users exactly how the system worked made them more likely to participate in grid-friendly charging.

Small incentives drive big changes.

The gamification elements transformed charging from a chore into something drivers looked forward to.

Design for the ecosystem, not just the user.

By considering the grid, the environment, and the driver together, we created a solution that worked for everyone.

Back to → Portfolio Home